Triple

T21792790
Position Surface form Disambiguated ID Type / Status
Subject Paul Lange og Tora Parsberg E538014 entity
Predicate hasProtagonist P8706 FINISHED
Object Paul Lange NE NERFINISHED

How this triple was built (2 steps)

Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.

NER Named-entity recognition gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Paul Lange | Statement: [Paul Lange og Tora Parsberg, hasProtagonist, Paul Lange]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Paul Lange
Context triple: [Paul Lange og Tora Parsberg, hasProtagonist, Paul Lange]
  • A. Paul Lange chosen
    Paul Lange is the fictional title character of the Danish play "Paul Lange og Tora Parsberg," around whom the drama’s political and personal conflicts revolve.
  • B. Arthur Lange
    Arthur Lange was an American composer and arranger known for his prolific work on film scores during the early 20th century Hollywood era.
  • C. James Lindenberg
    James Lindenberg was an American engineer and entrepreneur known as a pioneer of Philippine television broadcasting.
  • D. August Lange
    August Lange was a Norwegian educator, author, and resistance member during World War II, known for his work in education and his involvement in the fight against Nazi occupation.
  • E. Karl Straube
    Karl Straube was a prominent German organist, choral conductor, and influential interpreter of Bach and Reger who served as Thomaskantor in Leipzig.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 batches)

The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.

Step Stage Batch ID Status When
creating Elicitation batch_69e0c47198f881908cb0d237266c10e9 completed April 16, 2026, 11:13 a.m.
NER Named-entity recognition batch_69f06221d1f4819089bb113d808d79c2 completed April 28, 2026, 7:30 a.m.
Created at: April 16, 2026, 6:52 p.m.